sparse coding

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs CVPR 2026 Hierarchical Concept Embedding & Pursuit for Interpretable Image Classification CVPR 2026 Oligodendrocyte-Driven Spiking Neural Model AAAI 2026 Stop Probing, Start Coding: Why Linear Probes and Sparse Autoencoders Fail at Compositional Generalization UAI 2026 Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation ICML 2025 Emergent Orientation Maps —— Mechanisms, Coding Efficiency and Robustness ICLR 2025 Lexico: Extreme KV Cache Compression via Sparse Coding over Universal Dictionaries ICML 2025 SINR: Sparsity Driven Compressed Implicit Neural Representations CVPR 2025 Sparse Fine-Tuning of Transformers for Generative Tasks ICCV 2025 SSC-VAE: Structured Sparse Coding Based Variational Autoencoder for Detail Preserved Image Reconstruction AAAI 2025 Decomposed Linear Dynamical Systems (dLDS) for learning the latent components of neural dynamics JMLR 2024 Exploring Memorization in Fine-tuned Language Models ACL 2024 Further Compressing Distilled Language Models via Frequency-aware Partial Sparse Coding of Embeddings CoNLL 2024 Improving Robustness to Model Inversion Attacks via Sparse Coding Architectures ECCV 2024 Inertial Algorithm with Dry Fraction and Convolutional Sparse Coding for 3D Localization with Light Field Microscopy AAAI 2024 Learning Sparse Codes with Entropy-Based ELBOs AISTATS 2024 Nonlinear dynamics of localization in neural receptive fields NeurIPS 2024 PaCE: Parsimonious Concept Engineering for Large Language Models NeurIPS 2024 Poisson Variational Autoencoder NeurIPS 2024 Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning NeurIPS 2024 An Inertial Block Majorization Minimization Framework for Nonsmooth Nonconvex Optimization JMLR 2023 Dictionary Learning for the Almost-Linear Sparsity Regime ALT 2023 Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks ICML 2023 Emergence of Shape Bias in Convolutional Neural Networks through Activation Sparsity NeurIPS 2023 Hiding Data Helps: On the Benefits of Masking for Sparse Coding ICML 2023